INDEX

Explanations

terms related to programming functions and data encoding

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

agar

-0.17

reuse

-0.16

eper

-0.16

etrics

-0.15

/connection

-0.14

ç«ŀ

-0.14

scratch

-0.14

rych

-0.13

anches

-0.13

à¹Ģà¸ĭ

-0.13

POSITIVE LOGITS

 transformation

0.38

 transform

0.34

 transformations

0.34

 Transformation

0.34

 Transform

0.33

 convert

0.33

Transform

0.32

transform

0.32

 transforms

0.32

_transform

0.31

Activations Density 0.341%

terms related to programming functions and data encoding

No Comments

No Known Activations